Sarvam
Sarvam 105B (high)
Quality Score12.4
Value Score15.2
Reliability20.3
Cache Discount38%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.042
- Output
- $0.170
- Cached Input
- $0.026
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 11.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- -59.4
- Correct
- 17.6%
- Blended price
- $0.044
Answer outcomes
Correct 17.6%Incorrect 77.0%Abstained 5.4%
Artificial Analysis benchmarks
- SciCode
- 26%
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 74%
- CritPt
- 0%
- AA-Omniscience
- 20%
- AA-LCR
- 0%
Similar models
- Sarvam 30B (high)SarvamQuality Score 7.0Value Score 9.1
- Motif-2-12.7B-ReasoningMotif TechnologiesQuality Score 11.6Value Score not available
- LFM2.5-2.6BLiquid AIQuality Score 11.4Value Score 11.8
- Gemma 4 E4B (Reasoning)GoogleQuality Score 13.9Value Score 13.8
- gpt-oss-20b (low)OpenAIQuality Score 12.7Value Score 16.2
- Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIAQuality Score 14.0Value Score 13.1